AI agents use add_layout_picture to create or update resources in QGIS MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your QGIS MCP environment.
The tool adds visual elements to a print layout, which modifies the project state reversibly. This is a write operation—it creates new layout objects without deleting or executing arbitrary code. The severity is medium because misuse could corrupt a layout design or embed unwanted images, but the impact is limited to the print layout and reversible.
From the tool's definition Tool description states 'Add a picture or SVG (logo, north arrow) to a print layout', which involves creating/modifying layout elements within a QGIS project.
Attacks that exploit this kind of access
Add a picture or SVG (logo, north arrow) to a print layout. path is an image. It is categorised as a Write tool in the QGIS MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the QGIS MCP server in PolicyLayer and add a rule for add_layout_picture: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches QGIS MCP. Nothing to install.
add_layout_picture is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the add_layout_picture rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for add_layout_picture. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
add_layout_picture is provided by the QGIS MCP server (nkarasiak/qgis-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →